DeepAI AI Chat
Log In Sign Up

ViTO: Vision Transformer-Operator

by   Oded Ovadia, et al.
Brown University
Tel Aviv University

We combine vision transformers with operator learning to solve diverse inverse problems described by partial differential equations (PDEs). Our approach, named ViTO, combines a U-Net based architecture with a vision transformer. We apply ViTO to solve inverse PDE problems of increasing complexity, namely for the wave equation, the Navier-Stokes equations and the Darcy equation. We focus on the more challenging case of super-resolution, where the input dataset for the inverse problem is at a significantly coarser resolution than the output. The results we obtain are comparable or exceed the leading operator network benchmarks in terms of accuracy. Furthermore, ViTO`s architecture has a small number of trainable parameters (less than 10 leading competitor), resulting in a performance speed-up of over 5x when averaged over the various test cases.


page 6

page 8

page 9

page 10

page 11

page 12


Physics Informed Token Transformer

Solving Partial Differential Equations (PDEs) is the core of many fields...

Multiwavelet-based Operator Learning for Differential Equations

The solution of a partial differential equation can be obtained by compu...

Learning to Solve PDE-constrained Inverse Problems with Graph Networks

Learned graph neural networks (GNNs) have recently been established as f...

Inverse Problem of Nonlinear Schrödinger Equation as Learning of Convolutional Neural Network

In this work, we use an explainable convolutional neural network (NLS-Ne...

Multi-objective discovery of PDE systems using evolutionary approach

Usually, the systems of partial differential equations (PDEs) are discov...

GNOT: A General Neural Operator Transformer for Operator Learning

Learning partial differential equations' (PDEs) solution operators is an...